Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free
idapt Code

Boundaries

Give a coding agent only the access the task needs

idapt Code adds no permission mode of its own. It runs inside the computer policy, workspace permissions, and Secret-injection controls that already govern every agent computer command.

Start codingRead the quickstart
Computer policy stays authoritative

Pairing and command authorization are separate. The skill reports missing access instead of changing daemon policy.

Secrets are referenced by name

Store a token in workspace Secrets and inject it into the single command that needs it. Secret values never enter the prompt.

Delivery is explicit

The skill asks before destructive operations, and commits, pushes, or opens a pull request only when the task calls for it.

Know the boundary

An agent that can run commands can intentionally read data available to that operating-system account. Redaction reduces accidental disclosure, but it cannot make an untrusted command safe.

See workspace Secrets

The rest of idapt Code

On your computer

AI coding on a computer you control

On a cloud computer

A fresh cloud computer for the task

Choosing a model

Use the model that fits each coding task

Give it a project and one concrete task.

Pick a paired or cloud computer, name the project, and say what done looks like.

Start codingRead the docs

Read the docs

  • idapt Code quickstart
  • Pair a computer
  • Use Secrets safely

Pair with

  • Computers
  • Cloud Computers
  • Local AI
  • Tunnels
  • Skills
  • Home
  • Pricing
  • AI Models
  • Image models
  • Voice models
  • Video models
  • Rankings
  • New models
  • Model status
  • Multi-Model Chat
  • Voice Mode
  • Voice HUD
  • Web Search
  • Image Generation
  • Video Generation
  • Audio Generation
  • Transcription
  • Drive
  • Secrets
  • Sharing
  • Workspaces
  • Tasks
  • Memory
  • Agents
  • Subagents
  • Automations
  • Skills
  • idapt Code
  • Code Execution
  • Computers
  • Computer Use
  • Computer Assist · Soon
  • Cloud Computers
  • Local AI
  • AI Gateway
  • API & SDK
  • CLI
  • MCP
  • Tunnels
  • All features →
  • LLM cost calculator
  • Token counter
  • Context window checker
  • Can I run it
  • Model picker quiz
  • Savings finder
  • Video cost estimator
  • Text to speech cost
  • Transcription cost
  • API endpoint tester
  • All free tools →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Learn
  • Prompts
  • Templates
  • Changelog
  • Help center
  • FAQ
  • Privacy
  • Compare all models
  • Support
  • idapt Code
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)